© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73528
    Prev
    Next
    INDEX
    Explanations

    introducing examples or points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÈNE
    -1.04
    pegno
    -1.04
    Trin
    -1.04
    당
    -1.04
    rophoto
    -1.03
    ³/
    -1.03
    tà
    -1.02
    tuje
    -1.01
     but
    -0.99
    inol
    -0.98
    POSITIVE LOGITS
    ,
    1.20
    ⽣
    1.16
    ラックス
    1.13
     Institutionen
    1.09
     ilustracji
    1.06
    ਖ਼
    1.05
     Už
    1.04
    для
    1.03
     berbagai
    1.03
     Gesamt
    1.02
    Activations Density 0.130%

    No Known Activations